<html><body>
<p><tt>Roland Dreier <rdreier@cisco.com> wrote on 06/25/2008 01:07:04 PM:<br>
<br>
> Would a better fix to add locking around the "assume HW is wedged"<br>
> code in ipoib_cm_dev_stop() to avoid problems if the 5 second timeout is<br>
> too short?<br>
> <br>
> - R.<br>
</tt><br>
<tt>According to our stress test, 5 second timeout is way too short. What do you mean by add locking there?</tt><br>
<br>
<tt>Thanks</tt><br>
<tt>Shirley</tt></body></html>